Smart Data & Knowledge Services

Humans can accomplish a variety of tasks because they have the ability to understand problems, abstract them appropriately, and then combine their knowledge with their experience to develop appropriate solutions. Humans are able to learn from problem solving experience and thus continuously improve themselves, be it by accomplishing tasks better, with fewer mistakes, or faster. At the DFKI branch at the University of Trier, we investigate experience-based learning systems in which we try to transfer comparable mechanisms of problem solving and learning to computer systems and implement them in different areas. Experience-based learning systems are hybrid AI systems that use different AI technologies:

• Semantic technologies (ontologies, knowledge graphs)
• Case-Based Reasoning (CBR) & Process-Oriented Case-Based Reasoning (POCBR)
• Machine Learning, incl. Deep Learning
• Planning and Constraint Satisfaction Problem-Solving

Application Area Intelligent Process Management

Increasing digitalization as well as today's requirements regarding the flexibility of production and service provision call for new intelligent approaches to process management using artificial intelligence methods. To this end, we are researching experience-based learning systems with which the redesign, adaptation and optimization of processes is possible, the execution of processes can be supported by flexible workflow systems and the analysis of process data can be performed with regard to the diagnosis of resources and processes.

Current applications and projects at the University of Trier:

• Industrie 4.0: flexible production and predictive maintenance
• Craft: work processes in defect management in the construction industry
• Agriculture: application process for subsidies
• Medicine: analysis of clinical processes
• Culinary: generation of new cooking recipes
• E-Science: scientific workflows for the analysis of scientific data

Application Area Knowledge and Experience Management in the Digital Society

In the modern, digital knowledge society, knowledge and experience must increasingly be networked on a global scale and made available, assessable, and usable. We explore how experience-based learning systems can understand and analyze knowledge and experience in available (mostly textual) forms, and how efficient search and decision support can be realized based on this.

Current applications and projects at the University of Trier:

• Political Science: analysis and synthesis of argumentation
• Legal Science: decision support in data protection law
• Business documents: Information extraction and process integration
• Service: analysis of service reports for search and decision support

For the practical implementation of experience-based learning systems, we develop the Java-based ProCAKE (Process-Oriented Case-Based Knowledge Engine) framework, which we use in various projects and continuously extend.

Publications:

http://www.wi2.uni-trier.de/shared/publications/DFKIPub.html